Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Automatic cartoon generation method and system based on BBWC model and MCMC

A technology of models and comics, applied in neural learning methods, biological neural network models, natural language data processing, etc., can solve the problem of losing the details of the original image

Pending Publication Date: 2021-02-26
WUHAN UNIV
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This method is simple to implement, but it will lose some details of the original image

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Automatic cartoon generation method and system based on BBWC model and MCMC
  • Automatic cartoon generation method and system based on BBWC model and MCMC
  • Automatic cartoon generation method and system based on BBWC model and MCMC

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0123]The present invention belongs to computer and information service technology, and particularly relates to a method and system for automatically generating semantic comics by recognizing Chinese natural language text. The present invention proposes an automatic comic generation method based on the BBWC model and MCMC, through which comics conforming to the semantics of the input text can be automatically generated. The system flow structure diagram is asfigure 1 Shown.

[0124]The present invention can use a computer to train and infer the network, and is implemented by using the Tensorflow deep learning framework under the windows operating system. The specific experimental environment configuration is as follows:

[0125]

[0126]Step 1. Annotate people, place names, institution names, common nouns, numerals, prepositions, and locality words in a Chinese data set composed of fairy tales, fables, and novels for training named entity recognition in the natural language processing stage ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention provides an automatic cartoon generation method and system based on a BBWC model and an MCMC. The method comprises the following steps: firstly, carrying out entity labeling of an extended range on a Chinese data set; secondly, designing a BERTBiLSTM + WSCRF named entity recognition model, and training on the marked data set to recognize seven types of entities including names, placenames, organization names, common nouns, numerals, prepositions and nouns so as to obtain information such as foreground object types, background templates and the number and position relation of theforeground object types and the background templates; defining different scene templates to describe different scenes so as to supplement scene information; then selecting a proper template accordingto the previously obtained information; then, controlling the scene layout by an MCMC method to generate complete scene information; achieving seamless fusion of multiple image materials by a Poissonfusion algorithm; and finally, inputting the text into the final model, and automatically generating a cartoon conforming to semantics. According to the invention, the size, proportion and position relationship of each image can be reasonably controlled; Seamless fusion of multiple image materials can be realized.

Description

Technical field[0001]The present invention belongs to computer and information service technology, and particularly relates to a method and system for automatically generating semantic comics by recognizing Chinese natural language text.Background technique[0002]In modern life, people come into contact with thousands of image information from various channels every day, but even so, when people search for images, especially when the search sentence is a long sentence, it is still difficult to obtain in mainstream search engines. Images that fully comply with the semantic information of the search sentence. In this case, if you can realize the understanding of the input sentence and directly generate images that match the semantics, you will get more satisfactory results. Comics, as a kind of image category that is well-loved by the public, can be automatically generated by applying natural language processing, image synthesis and other technologies to automatically generate comics, ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06F40/295G06F40/30G06F16/33G06N3/04G06N3/08G06T5/50G06T11/60
CPCG06F40/295G06F40/30G06F16/3344G06N3/049G06N3/08G06T11/60G06T5/50G06N3/044
Inventor 李治江应德浩李宇涛蔡文晖
Owner WUHAN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products